Quick links

The Barrelfish OS for Hetergeneous Multicore Systems

Date and Time
Friday, December 5, 2008 - 3:00pm to 4:30pm
Location
Friend Center 013
Type
Seminar
Speaker
Timothy Roscoe
Host
Larry Peterson
The Barrelfish OS is a new open-source operating system for heterogeneous multicore systems being developed at ETH Zurich, in conjunction with Microsoft Research in Cambridge.

This talk will say why we think we can write a new OS, and why we think we should. Hand-in-hand with increasing hardware parallelism is increasing hardware diversity, even within a single machine. Furthermore, the drive towards multicore programmability is beginning to result in interesting language and runtime features whose I/O and scheduling requirements may not be well served by existing OS structure.

Barrelfish seeks to meet these challenges by viewing a multicore machine more as a networked system than as a single, monolithic computer, and applying results from distributed computing to scaling a single OS instance across many heterogeneous cores. We also apply knowledge representation techniques to allow the OS and applications to reason about the richness of the hardware at runtime, in the interests of continuous performance optimization. I'll talk about how these approaches lead to a novel way of structuring an OS, and the current status and future directions of the system. ork).ABSTRACT: The Barrelfish OS is a new open-source operating system for heterogeneous multicore systems being developed at ETH Zurich, in conjunction with Microsoft Research in Cambridge. This talk will say why we think we can write a new OS, and why we think we should. Hand-in-hand with increasing hardware parallelism is increasing hardware diversity, even within a single machine. Furthermore, the drive towards multicore programmability is beginning to result in interesting language and runtime features whose I/O and scheduling requirements may not be well served by existing OS structure. Barrelfish seeks to meet these challenges by viewing a multicore machine more as a networked system than as a single, monolithic computer, and applying results from distributed computing to scaling a single OS instance across many heterogeneous cores. We also apply knowledge representation techniques to allow the OS and applications to reason about the richness of the hardware at runtime, in the interests of continuous performance optimization. I'll talk about how these approaches lead to a novel way of structuring an OS, and the current status and future directions of the system.

Follow us: Facebook Twitter Linkedin